检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Kurenkov, Vladislav Hamed, Hany Savin, Sergei Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Robotics Institute Innopolis University Innopolis Russia

In this paper, we consider tensegrity hopper - a novel tensegrity-based robot, capable of moving by hopping. The paper focuses on the design of the stabilizing control policies, which are obtained with Augmented Random Search method. In particular, we search for control policies which allow the hopper to maintain vertical stability after performing a single jump. It is demonstrated, that the hopper can maintain a vertical configuration, subject to the different initial conditions and with changing control frequency rates. In particular, lowering control frequency from 1000Hz in training to 500Hz in execution did not affect the success rate of the balancing task. Copyright © 2020, The Authors. All rights reserved.

关键词： Hoppers

来源：评论

学校读者我要写书评

暂无评论

Real-Time Long Range Trajectory Replanning for MAVs in the Presence of Dynamic Obstacles

Real-Time Long Range Trajectory Replanning for MAVs in the P...

引用

Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)

作者： Geesara Kulathunga Roman Fedorenko Sergey Kopylov Alexandr Klimehik Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia

ISBN: (数字)9781728198187

ISBN: (纸本)9781728198194

Real-time long-range local planning is a challenging task, especially in the presence of dynamics obstacles. We propose a complete system which is capable of performing the local replanning in real-time. Desired trajectory is needed in the system initialization phase; system starts initializing sub-components of the system including point cloud processor, trajectory estimator and planner. Afterwards, the multi-rotary aerial vehicle starts moving on the given trajectory. When it detects obstacles, it replans the trajectory from the current pose to pre-defined distance incorporating the desired trajectory. Point cloud processor is employed to identify the closest obstacles around the vehicle. For replanning, Rapidly-exploring Random Trees (RRT*) is used with two modifications which allow planning the trajectory in milliseconds scales. Once we replanned the desired path, velocity components(x,y and z) and yaw rate are calculated. Those values are sent to the controller at a constant frequency to maneuver the vehicle autonomously. Finally, we have evaluated each of the components separately and tested the complete system in the simulated and real environments.

关键词： Trajectory Planning Three-dimensional displays Real-time systems Splines (mathematics) Smoothing methods Message systems

来源：评论

学校读者我要写书评

暂无评论

Path Planning Followed by Kinodynamic Smoothing for Multirotor Aerial Vehicles (MAVs)

Path Planning Followed by Kinodynamic Smoothing for Multirot...

引用

Nonlinearity, Information and robotics, (NIR) International Conference

作者： Geesara Kulathunga Dmitry Devitt Roman Fedorenko Sergei Savin Alexandr Klimchik Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia

ISBN: (数字)9781728187631

ISBN: (纸本)9781728187648

We explore path planning followed by kinodynamic smoothing while ensuring the vehicle dynamics feasibility for MAVs. We have chosen a geometrically based motion planning technique "RRT*" for this purpose. In the proposed technique, we modified original RRT* introducing an adaptive search space and a steering function which help to increase the consistency of the planner. Moreover, we propose multiple RRT* which generates a set of desired paths, provided that the optimal path is selected among them. Then, apply kinodynamic smoothing, which will result in dynamically feasible as well as obstacle-free path. Thereafter, a b spline-based trajectory is generated to maneuver vehicle autonomously in unknown environments. Finally, we have tested the proposed technique in various simulated environments.

关键词： Smoothing methods Planning Trajectory Vehicle dynamics Splines (mathematics) Robots

来源：评论

学校读者我要写书评

暂无评论

Application of CycleGAN-based Augmentation for Autonomous Driving at Night

Application of CycleGAN-based Augmentation for Autonomous Dr...

引用

Nonlinearity, Information and robotics, (NIR) International Conference

作者： Vladislav Ostankovich Rauf Yagfarov Maksim Rassabin Salimzhan Gafurov Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russian Federation

ISBN: (数字)9781728187631

ISBN: (纸本)9781728187648

Self-driving vehicles contain a number of modules allowing them to autonomously navigate in uncertain environment. The robust, efficient, safe and accurate autonomous navigation are heavily depend on parameters of a perception module. In this paper, we consider perception module as a combination of object detection and road segmentation submodules. As a matter of fact, all of them are based on Deep learning technique. It leads to liability of a big training datasets to provide the accuracy, efficiency and robustness of a perception module for a self-driving car operating in a wide range of scenarios. This paper presents the GAN-based augmentation as a key factor allowing to improve the performances of perception. The provided research shows the comparison between classical augmentation method and CycleGAN-based method. The main focus is made on detection and segmentation problems at nights. The initial training data includes BDD100K dataset and our own one collected in winter time by means of front-view camera of a self-driving car developed in innopolis university. The obtained results show the improvement of segmentation task in case of application of CycleGAN augmentation. However, the chosen method of GAN-based augmentation has not shown the positive influence on object detection due to appeared visual artifacts.

关键词： Training Visualization Roads Training data Object detection Autonomous automobiles Task analysis

来源：评论

学校读者我要写书评

暂无评论

EEG features during maintaining a human body balance.

EEG features during maintaining a human body balance.

引用

Nonlinearity, Information and robotics, (NIR) International Conference

作者： Vladimir Khorev Vadim Grubov Artem Badarin Vladimir Maksimenko Center for technologies in robotics and mechatronics components Innopolis University Russia

ISBN: (数字)9781728187631

ISBN: (纸本)9781728187648

We have conducted an experiment involving keeping balance on a platform to research the perception of maintaining body posture. The objective of the present work was to characterize the common features of cortical activity during postural control. Regarding the cortical basis of performance differences during unstable conditions, EEG analysis suggest that central-frontal areas may underlie the cortical interaction including oscillations in general, maybe underlie cortical monitoring of changes in postural state of the body. The obtained results show that the neuronal activity in the β-frequency band can be utilized as the neurophysiological marker of the subject's ability to maintain the equilibrium state.

关键词： Training Process control Robot sensing systems Electroencephalography Stability analysis Task analysis Oscillators

来源：评论

学校读者我要写书评

暂无评论

Regions of Interest Segmentation from LiDAR Point Cloud for Multirotor Aerial Vehicles

Regions of Interest Segmentation from LiDAR Point Cloud for ...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Geesara Kulathunga Roman Fedorenko Alexandr Klimchik Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia

ISBN: (数字)9781728142784

ISBN: (纸本)9781728142791

We propose a novel filter for segmenting the regions of interest from LiDAR 3D point cloud for multirotor aerial vehicles. It is specially targeted for real-time applications and works on sparse LiDAR point clouds without preliminary mapping. We use this filter as a crucial component of fast obstacle avoidance system for agriculture drone operating at low altitude. As the first step, each point cloud is transformed into a depth image and then identify places near to the vehicle (local maxima) by locating areas with high pixel densities. Afterwards, we merge the original depth image with identified locations after maximizing intensities of pixels in which local maxima were obtained. Next step is to calculate the range angle image that represents angles between two consecutive laser beams based on the improved depth image. Once the corresponding range angle image is constructed, smoothing is applied to reduce the noise. Finally, we find out connected components within the improved depth image while incorporating smoothed range angle image. This allows separating the regions of interest. The filter has been tested on various simulated environments as well as an actual drone and provides real-time performance. We make our source code, dataset 2 and real world experiment 3 available online.

关键词： Three-dimensional displays Laser radar Laser beams Smoothing methods Two dimensional displays Real-time systems Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Real-time long range trajectory replanning for MAVs in the presence of dynamics obstacles

arXiv

引用

arXiv 2020年

作者： Kulathunga, Geesara Fedorenko, Roman Kopylov, Sergey Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia

—Real-time long-range local planning is a challenging task, especially in the presence of dynamics obstacles. We propose a complete system which is capable of performing the local replanning in real-time. Desired trajectory is needed in the system initialization phase;system starts initializing sub-components of the system including point cloud processor, trajectory estimator and planner. Afterwards, the multi-rotary aerial vehicle starts moving on the given trajectory. When it detects obstacles, it replans the trajectory from the current pose to pre-defined distance incorporating the desired trajectory. Point cloud processor is employed to identify the closest obstacles around the vehicle. For replanning, Rapidly-exploring Random Trees (RRT*) is used with two modifications which allow planning the trajectory in milliseconds scales. Once we replanned the desired path, velocity components(x,y and z) and yaw rate are calculated. Those values are sent to the controller at a constant frequency to maneuver the vehicle autonomously. Finally, we have evaluated each of the components separately and tested the complete system in the simulated and real environments. Copyright © 2020, The Authors. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Path planning followed by kinodynamic smoothing for multirotor aerial vehicles (MAVs)

arXiv

引用

arXiv 2020年

作者： Kulathunga, Geesara Prathap Devitt, Dmitry Fedorenko, Roman Savin, Sergei Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Detecting epileptic seizures using machine learning and interpretable features of human EEG

引用

The European Physical Journal Special Topics 2022年第5期232卷 673-682页

作者： Karpov, Oleg E. Afinogenov, Sergey Grubov, Vadim V. Maksimenko, Vladimir Korchagin, Sergey Utyashev, Nikita Hramov, Alexander E. National Medical and Surgical Center named after N. I. Pirogov Ministry of Healthcare of the Russian Federation Moscow Russia Faculty of Information Technology and Big Data Analysis Financial University under the Government of the Russian Federation Moscow Russia Baltic Center for Artificial Intelligence and Neurotechnology Immanuel Kant Baltic Federal University Kaliningrad Russia Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

Epilepsy is a neurological disorder distinguished by sudden and unexpected seizures. To diagnose epilepsy, clinicians register the signals of brain electric activity (electroencephalograms, EEG) and extract segments with seizures. It enables characterizing their type and finding an onset zone, a brain area where they originate. This procedure requires manual EEG deciphering, which is slow and necessitates the assistance of machine learning (ML) algorithms. Traditionally, ML handles this issue in a supervised fashion, i.e., after the training on the representative data, it constructs a boundary in the feature space that separates classes. As the number of features grows, this boundary becomes complex and less generalized. The feature space of brain data is high dimensional. The standard recording includes 30 signals and 50 frequencies resulting in 1500 features. Using additional time-domain features may further enlarge the feature space. Thus, selecting appropriate features is a big part of the successful classification. The selection procedure relies on either a data-based mathematical approach (e.g., principal components, PCs) or the expert domain knowledge of data (explainable features, EFs). Here, we demonstrate the benefits of using EFs. For the EEG data of 30 epileptic patients, we trained a RandomForest algorithm using PCs and EFs. The feature importance analysis revealed that explainable features outperform principal components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recurrence plot analysis of functional brain connectivity during bistable visual perception 3

Recurrence plot analysis of functional brain connectivity du...

引用

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Miftahova, Amina R. Hramov, Alexander E. Innopolis University Innopolis420500 Russia Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis420500 Russia

ISBN: (纸本)9781728124704

To develop fully-featured brain-computer interfaces it is crucial to study the behaviour of the brain in ambiguous situations. In this study, we analyzed the EEG data recorded during the perception of the bistable image - Necker's cube with the varying intensity of the lines. The image was demonstrated to the test person for one second and the person was asked to decide whether the cube is right-oriented or left-oriented and to push the corresponding data. During these actions the brain activity was recorded using 31-channel EEG, electrodes were placed according to the 10-20 system. The analysis, which was performed with the application of joint recurrence plots, suggests the existence of the synchronization between the channels of the frontal and occipital lobes. We believe that more rigorous research could reveal statistically significant brain connections and their dependence on physiological factors. Besides, this study may be significant for the development of the self-learning adaptive control systems. © 2019 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：